Sparse Explanations of Neural Networks Using Pruned Layer-Wise Relevance Propagation

arXiv:2404.14271v1 Announce Type: new
Abstract: Explainability is a key component in many applications involving deep neural networks (DNNs). However, current explanation methods for DNNs commonly leave it to the human observer to distinguish relevant explanations from spurious noise. This is not feasible anymore when going from easily human-accessible data such as images to more complex data such as genome sequences. To facilitate the accessibility of DNN outputs from such complex data and to increase explainability, we present a modification of …

abstract applications arxiv cs.lg current data explainability however human key layer networks neural networks noise propagation type wise